© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 16342
    Prev
    Next
    INDEX
    Explanations

    a variety of frequently used words, especially pronouns and words related to storytelling.

    oai_token-act-pair · gemini-2.0-flash

    works of art

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    libft
    -0.53
     kasarigan
    -0.52
    lijks
    -0.48
    htë
    -0.45
     cap
    -0.44
    ernoo
    -0.42
    infile
    -0.42
    __":
    -0.42
    MLLoader
    -0.42
     powi
    -0.42
    POSITIVE LOGITS
    errHandler
    0.68
     BorderSide
    0.57
    BufferException
    0.52
    devise
    0.51
    ressible
    0.50
    Applied
    0.50
    τσ
    0.50
    ]='\
    0.50
    ternut
    0.50
    íté
    0.49
    Activations Density 8.372%

    No Known Activations